Details
-
Improvement
-
Status: Resolved
-
Major
-
Resolution: Fixed
-
None
Description
Besides improvements of Neon any/all implementation, we can simplify below code
#ifdef ARROW_HAVE_NEON using simd_batch = xsimd::batch<int8_t, xsimd::neon64>; #else using simd_batch = xsimd::batch<int8_t, xsimd::sse4_2>; #endif
to
using simd_batch = xsimd::make_sized_batch_t<int8_t, 16>;
Attachments
Issue Links
- links to